Model Releases
Trained entirely in simulation: ~400,000 trajectories across 6,000 scenes. A prefix-caching recipe cuts training tokens by 22×, turning mont…
Trained entirely in simulation: ~400,000 trajectories across 6,000 scenes. A prefix-caching recipe cuts training tokens by 22×, turning months-long runs into days. Online RL (CISPO) pushes success rat
Trained entirely in simulation: ~400,000 trajectories across 6,000 scenes. A prefix-caching recipe cuts training tokens by 22×, turning months-long runs into days. Online RL (CISPO) pushes success rates higher still.
Source: Mistral AI (X) | 2026-07-08